LLM-groundedVideoDiffusion icon indicating copy to clipboard operation
LLM-groundedVideoDiffusion copied to clipboard

confusion regarding models in Notebook

Open GARV-k opened this issue 1 year ago • 3 comments

https://colab.research.google.com/drive/17He4bFAF8lXmT9Nfv-Sg29iKtPelDUNZ in the colab notebook you provided here, is the baseline model, the model proposed by you ?

GARV-k avatar Jun 13 '24 23:06 GARV-k

If you set lvd_gligen_scheduled_sampling_beta to 0, it is equivalent to not using the GLIGEN adapters trained in IGLIGEN project. This way it falls back to the original baseline model (since the adapters are not turned on).

TonyLianLong avatar Jun 14 '24 03:06 TonyLianLong

Yea but is that baseline model , the base model proposed by you. Or is the baseline model in the model some other model. I am really sorry for this confusion but this detail is important for my project.

GARV-k avatar Jun 14 '24 09:06 GARV-k

The base model is modelscope for square videos and zeroscope for horizontal videos.

TonyLianLong avatar Jun 15 '24 06:06 TonyLianLong